Extrapolation of causal effects – hopes, assumptions, and the extrapolator’s circle

Khosrowi, Donal

doi:10.1080/1350178x.2018.1561078

Cited by 22 publications

(27 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these cases, we proceed from a causal effect of X on an outcome Y estimated in A and endeavour to draw a conclusion about the X to Y -effect in a novel target B , where A and B can differ in various ways. A useful way of organizing these differences is to distinguish three layers of causal analysis (Khosrowi 2019). Differences can occur concerning: (1) the structure of causal mechanisms, for example, whether there is a causal relationship between certain variables or not; (2) the finer-grained details of individual causal relationships between variables, such as whether a relationship is best described linearly or non-linearly, or what values important structural parameters shaping these relationships take; and (3) the values of so-called modifying variables 3 , that is, variables that can meddle with the sign and magnitude of an effect.…”

Section: Extrapolation In Evidence-based Policymentioning

confidence: 99%

“…Statistical approaches have been proposed in the microeconometrics literature (Crump et al 2008; Hotz, Imbens, and Mortimer 2005; see Khosrowi 2019; Muller 2013, 2014, 2015 for discussions) and other proposals have since followed their general rationale (van Eersel, Koppenol-Gonzalez, and Reiss 2019). In enabling extrapolation even when populations differ relevantly, statistical approaches focus on differences in the distribution of modifying variables.…”

Section: Two Approaches To Extrapolationmentioning

confidence: 99%

“…In enabling such extrapolations, statistical approaches require a wide range of assumptions (see e.g., Khosrowi 2019; Muller 2013, 2014, 2015), including causal assumptions about A and B . Among other things, they require that populations only differ concerning how modifying variables are distributed, but not concerning whether a modifying variable that plays a role in A also influences an effect in B , or how, exactly, it does so.…”

Section: Two Approaches To Extrapolationmentioning

confidence: 99%

“…There is also a second, more principled challenge to be acknowledged when emphasizing the role of models in experiment-target inference: the extrapolator’s circle (Steel 2009; see also Khosrowi 2019). In a nutshell, the extrapolator’s circle cautions that the causal knowledge about a target required for an extrapolation must not be so comprehensive that we could answer our causal query on the basis of that knowledge alone.…”

Section: Experiment-model-target Inferencementioning

confidence: 99%

See 3 more Smart Citations

When Experiments Need Models

Khosrowi

2021

Philosophy of the Social Sciences

Self Cite

View full text Add to dashboard Cite

This paper argues that an important type of experiment-target inference, extrapolating causal effects, requires models to be successful. Focusing on extrapolation in Evidence-Based Policy, it is argued that extrapolation should be understood not as an inference from an experiment to a target directly, but as a hybrid inference that involves experiments and models. A general framework, METI, is proposed to capture this role of models, and several benefits are outlined: (1) METI highlights epistemically significant interactions between experiments and models, (2) reconciles some differences among existing accounts of experiment-target relationships, and (3) facilitates critical appraisal of inferential practices from experiments.

show abstract

Section: Extrapolation In Evidence-based Policymentioning

confidence: 99%

Section: Two Approaches To Extrapolationmentioning

confidence: 99%

Section: Two Approaches To Extrapolationmentioning

confidence: 99%

Section: Experiment-model-target Inferencementioning

confidence: 99%

See 2 more Smart Citations

When Experiments Need Models

Khosrowi

2021

Philosophy of the Social Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“… 15. See Khosrowi (2019) as a critical evaluation of comparative process-tracing as a research strategy in econometrics. …”

mentioning

confidence: 99%

Two Strands of Field Experiments in Economics: A Historical-Methodological Analysis

Nagatsu

Favereau

2019

Philosophy of the Social Sciences

View full text Add to dashboard Cite

While the history and methodology of laboratory experiments in economics have been extensively studied by philosophers, those of field experiments have not attracted much attention until recently. What is the historical context in which field experiments have been advocated? And what are the methodological rationales for conducting experiments in the field as opposed to in the lab? This article addresses these questions by combining historical and methodological perspectives. In terms of history, we show that the movement toward field experiments in economics has two distinct roots. One is the general orientation of medical and social sciences to evidence-based policy evaluation, which gave rise to randomized field experiments in economics (e.g., behavioral public policy, poverty alleviation policy). The other is an awareness of several methodological limitations of lab experiments in economics, which required practitioners to get out of the lab and into the field. In these senses, the movement is a consequence of influences from both outside and inside economics: the general evidence-based trend in policy science and an internal methodological development of experimental economics. In terms of methodology, we show that these two roots resulted in two somewhat different notions of “external validity” as methodological rationales of field experiment. Finally, we suggest that analysis of experiments as exhibits highlights a methodological strategy in which both strands complement each other.

show abstract

The Many Threats from Mechanistic Heterogeneity That Can Spoil Multimethod Research

Siewert

Beach

2023

Texts in Quantitative Political Analysis

View full text Add to dashboard Cite

The combination of cross-case and within-case analysis in Multi-Method Research (MMR) designs has gained considerable traction in the social sciences over the last decade. One reason for the popularity of MMR is grounded in the idea that different methods can complement each other, in the sense that the strengths of one method can compensate for the blind spots and weaknesses of another and vice versa. In this chapter, we critically address this core premise of MMR with an emphasis on the external validity of applying some cross-case method, like standard regression or Qualitative Comparative Analysis, in combination with case study analysis. After a brief overview of the rationale of MMR, we discuss in detail the problem of deriving generalizable claims about mechanisms in research contexts that likely exhibit mechanistic heterogeneity. In doing so, we clarify what we mean by mechanistic heterogeneity and where researchers should look for potential sources of mechanistic heterogeneity. Finally, we propose a strategy for progressively updating our confidence in the external validity of claims about causal mechanisms through the strategic selection of cases for within-case analysis based on the diversity of the population.

show abstract

Extrapolation of causal effects – hopes, assumptions, and the extrapolator’s circle

Cited by 22 publications

References 29 publications

When Experiments Need Models

When Experiments Need Models

Two Strands of Field Experiments in Economics: A Historical-Methodological Analysis

The Many Threats from Mechanistic Heterogeneity That Can Spoil Multimethod Research

Contact Info

Product

Resources

About